Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88053
    Prev
    Next
    INDEX
    Explanations

    respiratory protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omap
    -0.09
     paired
    -0.08
     eksper
    -0.08
     અનુ
    -0.08
    	def
    -0.08
    /navigation
    -0.08
     ecs
    -0.08
    Congrats
    -0.07
    nect
    -0.07
     Superstar
    -0.07
    POSITIVE LOGITS
     hearing
    0.09
     Hearing
    0.09
     Watt
    0.09
     Hör
    0.09
     poussi
    0.09
     Selbst
    0.08
     alve
    0.08
     Coch
    0.08
     Stro
    0.08
     Tob
    0.08
    Activations Density 0.004%

    No Known Activations